CN111261288A - Method for early identifying bipolar disorder based on BDNF - Google Patents
Method for early identifying bipolar disorder based on BDNF Download PDFInfo
- Publication number
- CN111261288A CN111261288A CN202010266717.6A CN202010266717A CN111261288A CN 111261288 A CN111261288 A CN 111261288A CN 202010266717 A CN202010266717 A CN 202010266717A CN 111261288 A CN111261288 A CN 111261288A
- Authority
- CN
- China
- Prior art keywords
- bipolar disorder
- score
- auxiliary
- data
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention relates to the technical field of mental disease detection of clinical medicine, in particular to a method for identifying bipolar disorder at an early stage based on BDNF, wherein a data acquisition module acquires a detection data set, a data extraction module divides the detection data set into a prediction model data set and an auxiliary model data set, a bipolar disorder morbidity risk prediction model carries out on the prediction model data set to acquire a bipolar disorder morbidity risk prediction probability value, a bipolar disorder auxiliary diagnosis model processes the auxiliary model data set to acquire a bipolar disorder auxiliary diagnosis probability value, the probability that a patient suffers from bipolar disorder can be clearly seen through the two probability values, the occurrence of misdiagnosis is greatly avoided, and a doctor can determine a proper treatment scheme in a short time by using the method, so that the diagnosis time is shortened, and the working efficiency and the accuracy of the diagnosis scheme are improved; meanwhile, the invention can be used as a patient or a family member of the patient to carry out self judgment on the patient or the patient, thereby improving the prognosis of the disease.
Description
Technical Field
The invention relates to the technical field of mental disease detection in clinical medicine, in particular to a BDNF-based method for early identifying bipolar disorder.
Background
Mental disorders are central nervous system disorders caused by disturbances of brain activity, which are characterized clinically by abnormalities in cognition, emotion, will, behavior, and the like. With the development of society, the competitive mechanism and the daily increase, various mental health problems are more prominent. Mental diseases have become a serious and costly public health problem worldwide, affecting people of different ages, different cultures, and different socioeconomic status.
Bipolar disorder is a common and serious mental disease, is mainly characterized by high and low mood and has the characteristic of chronic recurrent attacks. The mood states in patients with bipolar disorder mainly include (hypo) manic episodes, depressive episodes, mixed-state episodes, episodic episodes, and remission periods. Because the majority of patients with bipolar disorder develop a depressive state first, and about 70% of the patient's episodes manifest as depression, and the time in the manic phase is short, bipolar disorder is not readily identifiable by physicians and patients. Moreover, the clinical manifestations of bipolar disorder in the depressive phase have many similarities with those of depression, and diagnosis of bipolar disorder is difficult on the premise that manic or mixed episodes cannot be clarified. At present, psychiatrists in clinical practice mainly rely on highly subjective clinical interviews for diagnosis, misdiagnosis is easy to be made into simple depression, treatment is delayed, and improper use of antidepressants can cause patients to turn from depression to mania, so that huge medical resource waste and family life burden are caused. How to identify and predict the onset of bipolar disorder in early stage is a key issue in psychomedicine.
The current research on biological markers for early diagnosis of bipolar disorder mainly focuses on basic research such as hematology, genetics, imaging and the like, and results are inconsistent, so that the research has a long distance in practical clinical application.
In the research, BDNF (brain-derived neurotrophic factor) is found to be differently expressed in depressive disorder and bipolar disorder, which may be related to factors such as epigenetics and protein expression, and based on the point, a method and a system for early identifying bipolar disorder based on BDNF are necessary.
Disclosure of Invention
The invention breaks through the difficult problems in the prior art, and designs the method and the system which can predict the onset risk of the bipolar disorder and assist in diagnosing the onset probability of the bipolar disorder to achieve the early recognition of the bipolar disorder by detecting the BDNF of the patient with depressive episode.
In order to achieve the purpose, the invention designs a method for identifying bipolar disorder at early stage based on BDNF, which is characterized by comprising the following steps: the method comprises the following steps:
s1, the data acquisition module acquires a detection data set from the outside;
the S2 data extraction module classifies the detection data set into a prediction model data set and an auxiliary model data set;
s3, acquiring a prediction model data set by the bipolar disorder morbidity risk prediction model, and performing data processing to acquire a bipolar disorder morbidity risk prediction probability value;
s4, acquiring an auxiliary model data set by the aid of the bipolar disorder auxiliary diagnosis model, and performing data processing to acquire a bipolar disorder auxiliary diagnosis probability value;
and the result display module of S5 acquires the bipolar disorder morbidity risk prediction probability value and the bipolar disorder auxiliary diagnosis probability value for display.
Further, the test data set obtained in S1 includes age, plasma mRNA (messenger RNA) level, BDNF level, mBDNF (mature brain derived neurotrophic factor) level, proBDNF (brain derived neurotrophic factor precursor) level.
Further, the prediction model data set in S2 includes age, BDNF level, plasma mRNA level; the auxiliary model dataset includes age, mBDNF level, proBDNF level.
Further, the specific method of data processing by the bipolar disorder onset risk prediction model in S3 is as follows:
s31, preprocessing the BDNF level to obtain lnBDNF;
s32 is calculated according to the first formula of age-score:
acquiring an age score I;
s33 calculation formula according to mRNA-score: obtaining mRNA fraction of 124-plasma mRNA level multiplied by 8300;
s34 is calculated according to lnBDNF-score: the lnBDNF fraction is lnBDNF multiplied by 33-58, and the lnBDNF fraction is obtained;
s35, adding the obtained age score I, the mRNA score and the lnBDNF score to obtain a total bipolar disorder morbidity risk prediction score;
s36, obtaining the bipolar disorder incidence risk prediction probability value according to the conversion table of the total score-probability value of the bipolar disorder incidence risk prediction.
Further, the specific method of data processing performed by the bipolar disorder auxiliary diagnosis model in S4 is as follows:
s41 preprocesses the mBDNF level and the proBDNF level to obtain MPratio, wherein the specific preprocessing formula is
S42 according to age-score calculation formula two: obtaining an age score of two (age-15) multiplied by 0.42;
s43 according to the formula for MPratio-score calculation: acquiring an MPratio score, wherein the MPratio score is 100-MPratio multiplied by 8;
s44, adding the obtained age score two and the MPratio score to obtain a total diagnosis score for assisting the diagnosis of the bipolar disorder;
s45, obtaining the auxiliary diagnosis probability value of the bipolar disorder according to the auxiliary diagnosis total score-probability value conversion table of the bipolar disorder.
The invention also designs a system of the method for identifying the bipolar disorder at the early stage based on BDNF, which is characterized in that: the system comprises a data acquisition module, a data extraction module, a bipolar disorder morbidity risk prediction model, a bipolar disorder auxiliary diagnosis model and a result display module;
the data acquisition module is used for accessing/acquiring an external actual detection data set, and comprises 1 data extraction unit and a plurality of data classification units, wherein the data extraction unit is connected with each data classification unit by a data transmission channel;
the bipolar disorder onset risk prediction model is used for predicting the risk probability of onset of bipolar disorder;
the bipolar disorder auxiliary diagnosis model is used for calculating the bipolar disorder diagnosis auxiliary probability;
and the result display module is used for displaying the probability value of the onset risk prediction of the bipolar disorder and the probability value of the auxiliary diagnosis of the bipolar disorder.
Further, the model for predicting the onset risk of bipolar disorder comprises: the device comprises a prediction data preprocessing unit used for preprocessing partial data in a prediction model data set, a prediction data calculating unit used for calculating the preprocessed prediction data and the obtained scores of each residual data in the prediction model data set, a prediction score integrating unit used for summing the calculation results of the prediction data, and a prediction probability obtaining unit used for converting the prediction total sum and the probability value.
Further, the bipolar disorder-assisted diagnosis model comprises: the auxiliary model data processing device comprises an auxiliary data preprocessing unit used for preprocessing partial data in an auxiliary model data set, an auxiliary data calculating unit used for calculating the preprocessed auxiliary data and the obtained score of each residual data in the auxiliary model data set, an auxiliary score integrating unit used for summing the calculated result of the auxiliary data, and an auxiliary probability obtaining unit used for converting the auxiliary total score and the probability value.
Compared with the prior art, the method obtains the prediction probability value of the morbidity risk of the bipolar disorder and the auxiliary diagnosis probability value of the bipolar disorder through the detection and calculation of BDNF, can clearly display the probability of the patient suffering from the bipolar disorder, greatly avoids misdiagnosis, and can be used by a doctor to determine a proper treatment scheme in a short time, so that the diagnosis and treatment time is shortened, and the working efficiency and the accuracy of the diagnosis and treatment scheme are improved; meanwhile, the invention can be used as a patient or a family member of the patient to carry out self judgment on the patient or the patient, thereby improving the prognosis of the disease.
Drawings
Fig. 1 is a schematic flow chart of a BDNF-based method for early identification of bipolar disorder according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a data processing method performed by the bipolar disorder onset risk prediction model according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating a data processing method performed by the bipolar disorder-assisted diagnosis model according to an embodiment of the present invention.
Fig. 4 is a schematic system structure diagram of the BDNF-based method for early identification of bipolar disorder according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a model for predicting the onset risk of bipolar disorder according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a bipolar disorder-assisted diagnosis model according to an embodiment of the present invention.
Fig. 7 is a test card of the model for predicting the onset risk of bipolar disorder according to an embodiment of the present invention.
Fig. 8 is a test card of the bipolar disorder-assisted diagnosis model according to an embodiment of the present invention.
The method comprises the following steps of 1, 2, 3, 4, 1-1, 2-3, 3-3 and 3-4, wherein the data acquisition module is a data acquisition module, the data prediction module is a bipolar disorder morbidity risk prediction module, the bipolar disorder auxiliary diagnosis module is a bipolar disorder auxiliary diagnosis module, the result display module is a result display module, the data extraction unit is 1-1, the data classification unit is 1-2, the prediction data preprocessing unit is 2-1, the prediction data calculation unit is 2-2, the prediction data integration unit is 2-3, the prediction score integration unit is 2-4, the prediction probability acquisition unit is 3-1, the auxiliary data preprocessing unit is 3-2, the auxiliary data calculation unit is 3-3, the.
Detailed Description
The invention will be further described with reference to the accompanying drawings, but is not to be construed as being limited thereto.
Referring to fig. 1-3, the invention designs a BDNF-based method for early identification of bipolar disorder, which comprises the following steps:
the data acquisition module 1 of S1 acquires detection data sets including age, plasma mRNA level, BDNF level, mBDNF level, proBDNF level and the like from the outside, wherein the plasma mRNA level, the BDNF level, the mBDNF level and the proBDNF level are examination structures of a patient after the current depressive episode sampling and are cross-sectional data;
the S2 data extraction module classifies the detection data set into a prediction model data set and an auxiliary model data set, wherein the prediction model data set comprises age, BDNF level and plasma mRNA level; the auxiliary model dataset comprises age, mBDNF level, proBDNF level;
the method comprises the following steps that S3 bipolar disorder morbidity risk prediction model 2 obtains a prediction model data set and carries out data processing, and the specific processing method comprises the following steps:
s31, preprocessing the BDNF level to obtain lnBDNF;
s32 is calculated according to the first formula of age-score:
acquiring an age score I;
s33 calculation formula according to mRNA-score: obtaining mRNA fraction of 124-plasma mRNA level multiplied by 8300;
s34 is calculated according to lnBDNF-score: the lnBDNF fraction is lnBDNF multiplied by 33-58, and the lnBDNF fraction is obtained;
s35, adding the obtained age score I, the mRNA score and the lnBDNF score to obtain a total bipolar disorder morbidity risk prediction score;
s36, obtaining a bipolar disorder morbidity risk prediction probability value according to the bipolar disorder morbidity risk prediction total score-probability value conversion table;
the S4 bipolar disorder aided diagnosis model 3 obtains an aided model data set, and performs data processing, where the specific processing method is as follows:
s41 preprocesses the mBDNF level and the proBDNF level to obtain MPratio, wherein the specific preprocessing formula is
S42 according to age-score calculation formula two: obtaining an age score of two (age-15) multiplied by 0.42;
s43 according to the formula for MPratio-score calculation: acquiring an MPratio score, wherein the MPratio score is 100-MPratio multiplied by 8;
s44, adding the obtained age score two and the MPratio score to obtain a total diagnosis score for assisting the diagnosis of the bipolar disorder;
s45, obtaining a bipolar disorder auxiliary diagnosis probability value according to the bipolar disorder auxiliary diagnosis total score-probability value conversion table;
and the S5 result display module 4 acquires the bipolar disorder morbidity risk prediction probability value and the bipolar disorder auxiliary diagnosis probability value for display.
Accordingly, the conversion table of the total score-probability value of the bipolar disorder incidence risk prediction described in S36 is shown in table 1-1.
TABLE 1-1 conversion table of total score-probability value for prediction of onset Risk of bipolar disorder
It can be seen from the above table that when the obtained score is less than 100 minutes, the prediction probability value of the onset risk of the bipolar disorder is less than 10%, and the onset risk probability of the bipolar disorder of the patient can be judged to be extremely low by not counting specific values; when the obtained score is larger than 122 minutes, the prediction probability value of the onset risk of the bipolar disorder is larger than 95%, the onset risk probability of the bipolar disorder of the patient can be judged to be extremely high without counting specific numerical values, and the score is between 100 and 122 minutes, and the probability is obtained from the table 1-1 according to the principle of high.
Accordingly, the conversion table of total points-probability values for the aided diagnosis of bipolar disorder described in S45 is shown in tables 1 to 2.
TABLE 1-2 general score-probability value conversion table for auxiliary diagnosis of bipolar disorder
It can be seen from the above table that when the obtained score is greater than 100 minutes, the probability value of the auxiliary diagnosis of the bipolar disorder is greater than 96%, and the probability that the patient has the bipolar disorder is extremely high without counting specific values; when the obtained score is less than 50 minutes, the probability value of the auxiliary diagnosis of the bipolar disorder is less than 8 percent, and the probability that the patient has the bipolar disorder is extremely low by disregarding specific numerical values; and if the score is between 50 and 100, obtaining the probability from the table 1-2 according to the high principle.
Referring to fig. 4-6, the invention also designs a system of the method for identifying bipolar disorder at early stage based on BDNF, which comprises a data acquisition module 1, a data extraction module, a bipolar disorder morbidity risk prediction model 2, a bipolar disorder auxiliary diagnosis model 3 and a result display module 4;
the data acquisition module 1 is used for accessing/acquiring an external actual detection data set, and comprises 1 data extraction unit 1-1 and a plurality of data classification units 1-2, wherein the data extraction unit 1-1 is connected with each data classification unit 1-2 by a data transmission channel;
the bipolar disorder onset risk prediction model 2 is used for predicting the risk probability of onset of bipolar disorder;
the bipolar disorder auxiliary diagnosis model 3 is used for calculating the bipolar disorder diagnosis auxiliary probability;
and the result display module 4 is used for displaying the probability value of the onset risk prediction of the bipolar disorder and the probability value of the auxiliary diagnosis of the bipolar disorder.
Accordingly, the model 2 for predicting the risk of onset of bipolar disorder includes: the device comprises a prediction data preprocessing unit 2-1 for preprocessing partial data in a prediction model data set, a prediction data calculating unit 2-2 for calculating the preprocessed prediction data and the obtained scores of each data left in the prediction model data set, a prediction score integrating unit 2-3 for summing the calculation results of the prediction data, and a prediction probability obtaining unit 2-4 for converting the prediction total and the probability values.
Accordingly, the bipolar disorder-aided diagnosis model 3 includes: the auxiliary model data set comprises an auxiliary data preprocessing unit 3-1 used for preprocessing partial data in the auxiliary model data set, an auxiliary data calculating unit 3-2 used for calculating the preprocessed auxiliary data and the obtained score of each data remained in the auxiliary model data set, an auxiliary score integrating unit 3-3 used for summing the calculated result of the auxiliary data, and an auxiliary probability obtaining unit 3-4 used for converting the auxiliary total sum and the probability value.
In the specific implementation, referring to fig. 7 and 8 for convenience of carrying, the present invention further includes a bipolar disorder risk prediction test card and a bipolar disorder auxiliary diagnosis test card, so that in use, a layperson can quickly and directly know the own disease probability by using a numerical value corresponding method.
Accordingly, referring to fig. 7, the bipolar disorder incidence risk prediction test card includes a score line, an age line, an mRNA value line, an lnBDNF value line, a total score line, and a probability line.
Wherein, the fractional row starts from 0 minutes to ends at 100 minutes, a large interval is divided every 10 minutes, each large interval is further divided into 4 small intervals, and each small interval represents 2.5 minutes.
Wherein the age row starts at 18 years and ends at 38 years, and is divided into intervals every 1 year, the 18 year scale corresponds to the 0 point scale of the score row, and the 38 year scale corresponds to the 6 point scale of the score row.
Where the mRNA number rows begin with a reciprocal of 0.015 to end with a reciprocal of 0.003, with 0.015 corresponding to a 0 point scale and 0.003 corresponding to a 100 point scale, at every 0.001 division.
Wherein, the lnBDNF numerical line starts from 1.8 to ends from 3.8, and every 0.2 is divided into an interval, wherein the 1.8 scale corresponds to 0 graduation, and the 3.8 scale corresponds to 67.5 graduation.
Wherein, the total division line starts from 0 to 130 minutes and is divided into one large interval every 10 minutes, 5 small intervals are equally divided into each large interval, and each interval represents 2 minutes.
Wherein, the probability row starts from 0.1 to ends from 0.95, 0.1 corresponds to 98 divisions of the total division row, and 0.95 corresponds to 122 divisions of the total division row.
Accordingly, referring to fig. 8, the bipolar disorder-assisted diagnosis test card includes a score line, an age line, an MPratio value line, a total score line, and a probability line.
Wherein the score line is the same as the score line of the bipolar disorder incidence risk prediction test card.
Wherein, the age row starts from 15 years to 45 years, the 15 years scale corresponds to the 0-point scale of the point row, and the 45 years scale corresponds to the 12.5-point scale of the point row.
Wherein, MPratio numerical value row divides 12 intervals from 12 beginning reciprocal numbers to 0 end, 12 scales correspond to 0 scale of fraction row, 0 scale corresponds to 100 scale of fraction row.
Wherein, the total division row is from 0 to 110 minutes, every 10 minutes is divided into a large interval, 5 small intervals are equally divided into each large interval, and each small interval represents 2 minutes.
Wherein, the probability row starts from 0.01 to ends at 0.95, the 0.01 scale corresponds to the 26-division scale of the total branch row, the 0.1 scale corresponds to the 50-division scale of the total branch row, and the 0.95 scale corresponds to the 100-division scale of the total branch row.
The risk of the occurrence of bipolar disorder can be predicted by the system for patients with a definite history of depressive episodes, both without (hypo) mania or with mixed episodes. Patients with bipolar disorders and patients with underlying bipolar characteristics can be screened for patients with depression episodes with both (hypo) manic episodes and mixed episodes unclear, thereby prompting and assisting the treating physician with the appropriate treatment regimen. The system can be used for assisting in diagnosing the bipolar disorder of a patient with the bipolar disorder in the mental examination, so that the treatment outcome is prevented from being influenced by misdiagnosis.
A specialist or a non-specialist can distinguish bipolar disorder and depression in a short time and predict the onset risk of the bipolar disorder according to the detection result of the plasma brain-derived neurotrophic factor mRNA and protein, so that the diagnosis and treatment time is shortened, the working efficiency and the accuracy of a diagnosis and treatment scheme are improved, and targeted treatment is given.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and additions can be made without departing from the method of the present invention, and these modifications and additions should also be regarded as the protection scope of the present invention.
Claims (8)
1. A method for early identification of bipolar disorder based on BDNF is characterized in that: the method comprises the following steps:
s1, the data acquisition module (1) acquires a detection data set from the outside;
the S2 data extraction module classifies the detection data set into a prediction model data set and an auxiliary model data set;
s3 the bipolar disorder morbidity risk prediction model (2) obtains a prediction model data set and carries out data processing to obtain a bipolar disorder morbidity risk prediction probability value;
s4 the auxiliary diagnosis model (3) of the bipolar disorder obtains an auxiliary model data set and processes the data to obtain the auxiliary diagnosis probability value of the bipolar disorder;
and the result display module (4) of S5 acquires and displays the bipolar disorder morbidity risk prediction probability value and the bipolar disorder auxiliary diagnosis probability value.
2. The BDNF-based method for early identification of bipolar disorder according to claim 1, wherein: the test data set obtained in S1 included age, plasma mRNA levels, BDNF levels, mBDNF levels, proBDNF levels.
3. The BDNF-based method for early identification of bipolar disorder according to claim 1, wherein: the prediction model data set in S2 includes age, BDNF levels, plasma mRNA levels; the auxiliary model dataset includes age, mBDNF level, proBDNF level.
4. The BDNF-based method for early identification of bipolar disorder according to claim 1, wherein: the specific method of data processing by the bipolar disorder onset risk prediction model (2) in S3 is as follows:
s31, preprocessing the BDNF level to obtain lnBDNF;
s32 is calculated according to the first formula of age-score:
acquiring an age score I;
s33 calculation formula according to mRNA-score: obtaining mRNA fraction of 124-plasma mRNA level multiplied by 8300;
s34 is calculated according to lnBDNF-score: the lnBDNF fraction is lnBDNF multiplied by 33-58, and the lnBDNF fraction is obtained;
s35, adding the obtained age score I, the mRNA score and the lnBDNF score to obtain a total bipolar disorder morbidity risk prediction score;
s36, obtaining the bipolar disorder incidence risk prediction probability value according to the conversion table of the total score-probability value of the bipolar disorder incidence risk prediction.
5. The BDNF-based method for early identification of bipolar disorder according to claim 1, wherein: the specific method of data processing by the bipolar disorder auxiliary diagnosis model (3) in S4 is as follows:
s41 preprocesses the mBDNF level and the proBDNF level to obtain MPratio, wherein the specific preprocessing formula is
S42 according to age-score calculation formula two: obtaining an age score of two (age-15) multiplied by 0.42;
s43 according to the formula for MPratio-score calculation: acquiring an MPratio score, wherein the MPratio score is 100-MPratio multiplied by 8;
s44, adding the obtained age score two and the MPratio score to obtain a total diagnosis score for assisting the diagnosis of the bipolar disorder;
s45, obtaining the auxiliary diagnosis probability value of the bipolar disorder according to the auxiliary diagnosis total score-probability value conversion table of the bipolar disorder.
6. A system for a BDNF early identification of bipolar disorder based on any one of the claims 1-5, wherein: the bipolar disorder diagnosis and treatment system comprises a data acquisition module (1), a data extraction module, a bipolar disorder morbidity risk prediction model (2), a bipolar disorder auxiliary diagnosis model (3) and a result display module (4);
the data acquisition module (1) is used for accessing/acquiring an external actual detection data set, and comprises 1 data extraction unit (1-1) and a plurality of data classification units (1-2), wherein the data extraction unit (1-1) is connected with each data classification unit (1-2) by a data transmission channel;
the bipolar disorder onset risk prediction model (2) is used for predicting the risk probability of onset of the bipolar disorder;
the bipolar disorder auxiliary diagnosis model (3) is used for calculating a bipolar disorder diagnosis auxiliary probability;
and the result display module (4) is used for predicting the occurrence risk prediction probability value of the bipolar disorder and the auxiliary diagnosis probability value of the bipolar disorder.
7. The system of claim 6, wherein the BDNF early identification method based on the BDNF is characterized in that: the bipolar disorder onset risk prediction model (2) comprises: the device comprises a prediction data preprocessing unit (2-1) used for preprocessing partial data in a prediction model data set, a prediction data calculating unit (2-2) used for calculating the preprocessed prediction data and the obtained score of each residual data in the prediction model data set, a prediction score integrating unit (2-3) used for summing the calculation results of the prediction data, and a prediction probability obtaining unit (2-4) used for converting the prediction total and the probability value.
8. The system of claim 6, wherein the BDNF early identification method based on the BDNF is characterized in that: the bipolar disorder-assisted diagnosis model (3) comprises: the auxiliary model data set comprises an auxiliary data preprocessing unit (3-1) used for preprocessing partial data in the auxiliary model data set, an auxiliary data calculating unit (3-2) used for calculating the preprocessed auxiliary data and the obtained score of each data in the auxiliary model data set, an auxiliary score integrating unit (3-3) used for summing the calculated result of the auxiliary data, and an auxiliary probability acquiring unit (3-4) used for converting the auxiliary total score and the probability value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010266717.6A CN111261288A (en) | 2020-04-07 | 2020-04-07 | Method for early identifying bipolar disorder based on BDNF |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010266717.6A CN111261288A (en) | 2020-04-07 | 2020-04-07 | Method for early identifying bipolar disorder based on BDNF |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111261288A true CN111261288A (en) | 2020-06-09 |
Family
ID=70955347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010266717.6A Pending CN111261288A (en) | 2020-04-07 | 2020-04-07 | Method for early identifying bipolar disorder based on BDNF |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111261288A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080081334A1 (en) * | 2006-08-04 | 2008-04-03 | Universidad Del Pais Vasco | Methods for diagnosis and pronostic of psychiatric diseases |
| WO2012113819A1 (en) * | 2011-02-23 | 2012-08-30 | Pangaea Biotech, S.L. | Molecular biomarkers for predicting response to antitumor treatment in lung cancer |
| CN108764541A (en) * | 2018-05-16 | 2018-11-06 | 天津大学 | A kind of wind energy prediction technique of combination space-time characteristic and Error processing |
| CN109431521A (en) * | 2018-10-12 | 2019-03-08 | 西北工业大学 | A kind of multi-modal bipolar depression automatic testing method based on audio/video information |
| CN109858454A (en) * | 2019-02-15 | 2019-06-07 | 东北大学 | One kind being based on dual model self-adaptive kernel correlation filtering method for tracing |
| CN110263937A (en) * | 2019-06-18 | 2019-09-20 | 深圳市腾讯网域计算机网络有限公司 | A kind of data processing method, equipment and storage medium |
| CN110634573A (en) * | 2019-09-27 | 2019-12-31 | 南昌大学第一附属医院 | Clinical cerebral infarction patient recurrence risk early warning scoring visualization model system and evaluation method thereof |
| CN110674726A (en) * | 2019-09-20 | 2020-01-10 | 清华大学 | Skin disease auxiliary diagnosis method and system based on target detection and transfer learning |
| CN110739076A (en) * | 2019-10-29 | 2020-01-31 | 上海华东电信研究院 | medical artificial intelligence public training platform |
| US20210035689A1 (en) * | 2018-04-17 | 2021-02-04 | Bgi Shenzhen | Modeling method and apparatus for diagnosing ophthalmic disease based on artificial intelligence, and storage medium |
-
2020
- 2020-04-07 CN CN202010266717.6A patent/CN111261288A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080081334A1 (en) * | 2006-08-04 | 2008-04-03 | Universidad Del Pais Vasco | Methods for diagnosis and pronostic of psychiatric diseases |
| WO2012113819A1 (en) * | 2011-02-23 | 2012-08-30 | Pangaea Biotech, S.L. | Molecular biomarkers for predicting response to antitumor treatment in lung cancer |
| US20210035689A1 (en) * | 2018-04-17 | 2021-02-04 | Bgi Shenzhen | Modeling method and apparatus for diagnosing ophthalmic disease based on artificial intelligence, and storage medium |
| CN108764541A (en) * | 2018-05-16 | 2018-11-06 | 天津大学 | A kind of wind energy prediction technique of combination space-time characteristic and Error processing |
| CN109431521A (en) * | 2018-10-12 | 2019-03-08 | 西北工业大学 | A kind of multi-modal bipolar depression automatic testing method based on audio/video information |
| CN109858454A (en) * | 2019-02-15 | 2019-06-07 | 东北大学 | One kind being based on dual model self-adaptive kernel correlation filtering method for tracing |
| CN110263937A (en) * | 2019-06-18 | 2019-09-20 | 深圳市腾讯网域计算机网络有限公司 | A kind of data processing method, equipment and storage medium |
| CN110674726A (en) * | 2019-09-20 | 2020-01-10 | 清华大学 | Skin disease auxiliary diagnosis method and system based on target detection and transfer learning |
| CN110634573A (en) * | 2019-09-27 | 2019-12-31 | 南昌大学第一附属医院 | Clinical cerebral infarction patient recurrence risk early warning scoring visualization model system and evaluation method thereof |
| CN110739076A (en) * | 2019-10-29 | 2020-01-31 | 上海华东电信研究院 | medical artificial intelligence public training platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elbaz et al. | Risk tables for parkinsonism and Parkinson's disease | |
| Bagby et al. | Are there subtypes of alexithymia? | |
| Jason et al. | Measuring substantial reductions in functioning in patients with chronic fatigue syndrome | |
| Sigrist et al. | Early life maltreatment and resting-state heart rate variability: A systematic review and meta-analysis | |
| Smith et al. | Measuring health status: self-, interviewer, and physician reports of overall health | |
| Drenkard et al. | Racial disparities in the incidence of primary chronic cutaneous lupus erythematosus in the southeastern us: the Georgia lupus registry | |
| US20150046176A1 (en) | System and method for improving neurologist's workflow on alzeimer's disease | |
| Nao et al. | Adverse effects of the apolipoprotein E ε4 allele on episodic memory, task switching and gray matter volume in healthy young adults | |
| EP3653109A1 (en) | Aggravation estimation device and aggravation estimation program | |
| Qin et al. | Risk classification for conversion from mild cognitive impairment to Alzheimer's disease in primary care | |
| Theme Filha et al. | Measurements of reported morbidity and interrelationships with health dimensions | |
| Ladapo et al. | Clinical utility of a precision medicine test evaluating outpatients with suspected obstructive coronary artery disease | |
| Shirole et al. | Cardiac, diabetic and normal subjects classification using decision tree and result confirmation through orthostatic stress index | |
| Sikka et al. | Inconsistencies with screening for traumatic brain injury in spinal cord injury across the continuum of care | |
| Farzanehfar et al. | Sensor measurements can characterize fluctuations and wearing off in Parkinson’s disease and guide therapy to improve motor, non-motor and quality of life scores | |
| JP2011138376A (en) | Diagnosis support system | |
| Tanguay-Sabourin et al. | A data-driven biopsychosocial framework determining the spreading of chronic pain | |
| Nishita et al. | Temporal trends in cognitive function among community-dwelling older adults in Japan: Findings from the ILSA-J integrated cohort study | |
| CN111261288A (en) | Method for early identifying bipolar disorder based on BDNF | |
| WO2023216293A1 (en) | System and method for predicting dementia or mild cognitive disorder | |
| Gupta et al. | X-ECGNet: an interpretable DL model for stress detection using ECG in COVID-19 healthcare workers | |
| TW201629892A (en) | Physiological monitoring feedback system and operating method thereof | |
| CN116052877A (en) | Diabetes patient depression risk assessment method and assessment system construction method | |
| CN115101204A (en) | Model, equipment and storage medium for quantitatively evaluating depression risk based on blood biochemical indexes | |
| CN111938652A (en) | Application of artificial intelligence diagnosis mode in early diagnosis of bronchial asthma |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |